© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 26-LLAMASCOPE-RES-32K
    11. 28238
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to processes, actions, and conditions involving management or execution activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪIJäºĨ
    -0.20
    ä¸ĬäºĨ
    -0.19
    åĪ°äºĨ
    -0.19
    åĩºäºĨ
    -0.18
    ÑĦоÑĢми
    -0.18
    inded
    -0.17
    rador
    -0.17
    æĿ¥äºĨ
    -0.15
    биÑĢа
    -0.15
    ensis
    -0.15
    POSITIVE LOGITS
    owaÄĩ
    0.42
    нÑĥÑĤÑĮ
    0.36
    оваÑĤÑĮ
    0.35
    zyÄĩ
    0.34
    иÑĤÑĮ
    0.33
    ваÑĤÑĮ
    0.32
    аÑĤÑĮ
    0.32
    ÑĥваÑĤи
    0.32
    ÑĢаÑĤиÑĤÑĮ
    0.31
    ниÑĤÑĮ
    0.31
    Activations Density 0.042%

    No Known Activations